Method and Apparatus for Building Sales Tools by Mining Data from Websites

• US 20110258531A1
• Filed: 04/18/2011
• Published: 10/20/2011
• Est. Priority Date: 12/23/2005
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Gilbert, Mazin, Feng, Junlan, Bangalore, Srinivas, Wilpon, Jay Gordon
• Granted Patent: US 8,359,307 B2
• Time in Patent Office: Days
• US Class Current: 715/234
• CPC Class Codes: G06F 40/134 Hyperlinking
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions

Abstract

A website mining tool is disclosed that extracts information from, for example, a company'"'"'s website and presents the extracted information in a graphical user interface (GUI). In one embodiment, web pages from a website are stored in, for example, computer memory and a structure of the web pages is identified. A plurality of blocks of information is then extracted as a function of this structure and a category is assigned to each block of information. The elements in the blocks of information are then displayed, for example to a salesperson, as a function of these categories. In another embodiment, Document Object Modeling parsing is used to identify the structure of the web pages. In yet another embodiment, a support vector machine is used to categorize each block of information.

Claims

1. A method for extracting elements of information from a website comprising a plurality of Web pages, said method comprising:

identifying a structure associated with said plurality of web pages;

extracting a plurality of blocks of information from said web pages as a function of said structure;

assigning each block of information in said plurality of blocks of information to a category in a plurality of categories; and

identifying a plurality of elements of information in each block of information.

2. The method of claim 1 further comprising:

displaying said elements of information as a function of said plurality of categories.

3. The method of claim 1 wherein said step of identifying said structure comprises parsing said web pages using Document Object Model parsing.

4. The method of claim 1 wherein said step of assigning comprises identifying a category for each block of information using a classification technique.

5. The method of claim 4 wherein said classification technique comprises a support vector machine.

6. The method of claim 1 wherein said step of identifying said plurality of elements of information comprises identifying a plurality of seeds.

7. The method of claim 6 wherein said step of identifying said plurality of elements comprises identifying noun phrases as a function of said plurality of seeds.

8. The method of claim 7 wherein said step of identifying said plurality of elements comprises identifying existing patterns of said noun phrases and associating those phrases with new elements of information in said blocks of information.

9. The method of claim 1 wherein said elements of information comprise information identifying a company'"'"'s products or services.

10. The method of claim 1 wherein said elements of information comprise contact information.

11. A apparatus for extracting elements of information from a website comprising a plurality of Web pages, said apparatus comprising:

means for identifying a structure associated with said plurality of web pages;

means for extracting a plurality of blocks of information from said web pages as a function of said structure;

means for assigning each block of information in said plurality of blocks of information to a category in a plurality of categories; and

means for identifying a plurality of elements of information in each block of information.

12. The apparatus of claim 11 further comprising:

means for displaying said elements of information as a function of said plurality of categories.

13. The apparatus of claim 11 wherein said means for identifying said structure comprises means for parsing said web pages using Document Object Model parsing.

14. The apparatus of claim 11 wherein said means for assigning comprises means for identifying a category for each block of information using a classification technique.

15. The apparatus of claim 14 wherein said classification technique comprises a support vector machine.

16. The apparatus of claim 11 wherein said means for identifying said plurality of elements of information comprises means for identifying a plurality of seeds.

17. The apparatus of claim 16 wherein said means for identifying said plurality of elements comprises means for identifying noun phrases as a function of said plurality of seeds.

18. The apparatus of claim 17 wherein said means for identifying said plurality of elements comprises means for identifying existing patterns of said noun phrases and associating those phrases with new elements of information in said blocks of information.

19. The apparatus of claim 11 wherein said elements of information comprise information identifying a company'"'"'s products or services.

20. The apparatus of claim 11 wherein said elements of information comprise contact information.

21. A computer readable medium storing computer program instructions which, when executed on a processor, define the steps of:

identifying a structure associated with a plurality of web pages on a Web site;

extracting a plurality of blocks of information from said web pages as a function of said structure;

assigning each block of information in said plurality of blocks of information to a category in a plurality of categories; and

identifying a plurality of elements of information in each block of information.

22. The computer readable medium of claim 21 further storing computer program instructions which, when executed on a processor, define the step of:

displaying said elements of information as a function of said plurality of categories.

23. The computer readable medium of claim 21 wherein said step of identifying said structure comprises parsing said web pages using Document Object Model parsing.

24. The computer readable medium of claim 21 wherein said step of assigning comprises identifying a category for each block of information using a classification technique.

25. The computer readable medium of claim 24 wherein said classification technique comprises a support vector machine.

26. The computer readable medium of claim 21 wherein said step of identifying said plurality of elements of information comprises identifying a plurality of seeds.

27. The computer readable medium of claim 26 wherein said step of identifying said plurality of elements comprises identifying noun phrases as a function of said plurality of seeds.

28. The computer readable medium of claim 27 wherein said step of identifying said plurality of elements comprises identifying existing patterns of said noun phrases and associating those phrases with new elements of information in said blocks of information.

29. The computer readable medium of claim 21 wherein said elements of information comprise information identifying a company'"'"'s products or services.

30. The computer readable medium of claim 21 wherein said elements of information comprise contact information.